Search

Identifying useful microseismic events is one of the key steps in monitoring tunnel rockbursts. Here, we propose a strong noise-tolerance deep learning (SNTDL) network for the automatic classification of noisy microseismic events. The training set, validation set, and test set of the SNTDL network consist of 27989 unfiltered microseismic recordings. First, to comprehensively characterize the microseismic events, we extract ten weakly correlated features of the microseismic recordings as the input of the SNTDL network. Then, the skip connection and concatenation structure are added to this network, which can further enhances its generalization ability. Additionally, the SNTDL, AlexNet, Inception, visual geometry group, and ResNet are compared using the synthetic microseismic recordings with different signal-noise ratios. The results demonstrate that the SNTDL network has a higher accuracy and stronger noise-tolerance capability than the other approaches. Application to a dataset collected from a different construction environment confirms that the SNTDL network can still achieve an accurate classification result, which further verifies that the proposed network has a reliable generalization performance. [ABSTRACT FROM AUTHOR]

One-way-broadcast-based flooding time synchronization algorithms are commonly used in wireless-sensor networks (WSNs). However, the packet delay and clock drift pose a challenge to accuracy, as they entail serious by-hop error accumulation problems in the WSNs. To overcome this, a rapid-flooding multibroadcast time synchronization with real-time delay compensation (RDC-RMTS) is proposed in this article. By using a rapid-flooding protocol, flooding latency of the referenced time information is significantly reduced in the RDC-RMTS. In addition, a new joint clock skew-offset maximum-likelihood estimation (MLE) is developed to obtain the accurate clock parameter estimations and the real-time packet delay estimation. Moreover, an innovative implementation of the RDC-RMTS is designed with an adaptive clock offset estimation. The experimental results indicate that the RDC-RMTS can easily reduce the variable delay and significantly slow the growth of by-hop error accumulation. Thus, the proposed RDC-RMTS can achieve accurate time synchronization in large-scale complex WSNs. [ABSTRACT FROM AUTHOR]

High spatial resolution tomographic gamma scanning (TGS) reconstruction is very important for the radioassay of drummed low-level radioactive waste. High spatial resolution means that the divided voxels are finer. Due to the large size of the drum, the traditional image reconstruction method based on complete samples takes a long time to scan. To limit the scanning time of the drum, sparse sampling is required. The maximum likelihood expectation maximization (MLEM) is widely used in TGS image reconstruction from projection data, but for high spatial resolution TGS imaging, its quality is insufficient to accurately describe the media boundary and determine radioactivity. The improved MLEM algorithm based on total variation (TV) regularization, such as the MLEM- TV minimization (TVM) algorithm, has been applied to reconstruct high spatial resolution TGS images. The split Bregman algorithm can quickly solve the partial differential equations of TV regularization. In this work, the split Bregman anisotropic TV (SBATV) and the split Bregman isotropic TV (SBITV) are the first time adopted to improve the iterative process of the MLEM algorithm, which are MLEM- SBATV and MLEM- SBITV. Experimental results show that both the MLEM- SBATV algorithm and the MLEM- SBITV algorithm can accurately reconstruct high spatial resolution TGS transmission images with sparse sampling. The MLEM- SBITV algorithm performs better in reconstructing the TGS emission images from sparse sampling than the traditional MLEM, MLEM- TVM, and MLEM- SBATV algorithms, increasing radionuclide positioning and radioactivity reconstruction accuracy. [ABSTRACT FROM AUTHOR]

Clock skew compensation is essential for accurate time synchronization in wireless networks. However, contemporary clock skew estimation is based on inaccurate transmission time measurement, which makes credible estimation challenging. Based on one-way broadcast synchronization, this article presents a novel maximum likelihood estimation (MLE) with an innovative implementation to minimize the clock skew estimation error caused by delay. A multiple one-way broadcast model is developed for observation and set collection, while the distribution of actual delay is discussed. A clock skew MLE based on Gaussian delay is then proposed and its Cramer–Rao lower bound provided. The developed MLE is independent of the clock offset estimation, and requires only two synchronization periods to generate an accurate estimation. Extensive experimental results indicate that the performance of the proposed MLE is better than the methods popularly used in existing time synchronization protocols. [ABSTRACT FROM AUTHOR]

Accurate and fast-convergent time synchronization is very important for wireless sensor networks. The flooding time synchronization converges fast, but its transmission delay and by-hop error accumulation seriously reduce the synchronization accuracy. In this article, a rapid-flooding multiple one-way broadcast time-synchronization (RMTS) protocol for large-scale wireless sensor networks is proposed. To minimize the by-hop error accumulation, the RMTS uses maximum likelihood estimations for clock skew estimation and clock offset estimation, and quickly shares the estimations among the networks. As a result, the synchronization error resulting from delays is greatly reduced, while faster convergence and higher-accuracy synchronization is achieved. Extensive experimental results demonstrate that, even over 24-hops networks, the RMTS is able to build accurate synchronization at the third synchronization period, and moreover, the by-hop error accumulation is slower when the network diameter increases. [ABSTRACT FROM AUTHOR]

Average consensus theory is intensely popular for building time synchronization in wireless sensor network (WSN). However, the average consensus-based time synchronization algorithm is based on the iteration that poses challenges for efficiency, as they entail high communication cost and long convergence time in large-scale WSN. Based on the suggestion that the greater the algebraic connectivity the faster the convergence, a novel multihop average consensus time synchronization (MACTS) is developed with innovative implementation in this article. By employing multihop communication model, it shows that virtual communication links among multihop nodes are generated and algebraic connectivity of the network increases. Meanwhile, a multihop controller is developed to balance the convergence time, accuracy, and communication complexity. Moreover, the accurate relative clock offset estimation is yielded by delay compensation. Implementing the MACTS based on the popular one-way broadcast model and taking multihop over short distances, we achieve hundreds of times the MACTS convergence rate compared to average TimeSync (ATS). [ABSTRACT FROM AUTHOR]

A Kalman-filter-based method is proposed to address challenges in nuclear signal processing, including pileup events and noise cancelation. The state-transition equation is established on the basis of suitable pulse shape models. By regarding the output signal of particle detectors as a measurable variable, the measurement equation is also introduced to correct dynamic processes of the state transition. A linear Kalman filter with $n$ tunnels is constructed to separate pileup events and maintain the original waveforms of pulses. In addition, two terms are defined and addressed for separation operations, namely, Availability, which is used to prepare for upcoming events, and Clearance Mechanism, which is given to remove thumbnail information from the previous events and make occupied tunnels available to subsequent nuclear events. Simulation and field experiments demonstrate that the proposed method can handle critical situations of pulse pileup and minimize count loss and dead time in the X-ray energy spectrum while maintaining the original pulse shapes. [ABSTRACT FROM AUTHOR]

Clustering analysis is a promising data-driven method for analyzing functional magnetic resonance imaging (fMRI) time series data. The huge computational load, however, creates practical difficulties for this technique. We present a novel approach, integrating principal component analysis (PCA) and supervised affinity propagation clustering (SAPC). In this method, fMRI data are initially processed by PCA to obtain a preliminary image of brain activation. SAPC is then used to detect different brain functional activation patterns. We used a supervised Silhouette index to optimize clustering quality and automatically search for the optimal parameter p in SAPC, so that the basic affinity propagation clustering is improved by applying SAPC. Four simulation studies and tests with three in vivo fMRI datasets containing data from both block-design and event-related experiments revealed that functional brain activation was effectively detected and different response patterns were distinguished using our integrated method. In addition, the improved SAPC method was superior to the k-centers clustering and hierarchical clustering methods in both block-design and event-related fMRI data, as measured by the average squared error. These results suggest that our proposed novel integrated approach will be useful for detecting brain functional activation in both block-design and event-related experimental fMRI data. [ABSTRACT FROM PUBLISHER]